Summary
International Symposium on Nonlinear Theory and Its Applications
2015
Session Number:B4L-E
Session:
Number:B4L-E-2
Basic Performances of Deterministic Particle Swarm Optimizer Networks
Tomoyuki Sasaki, Hidehiro Nakano, Arata Miyauchi, Akira Taguchi,
pp.720-723
Publication Date:2015/12/1
Online ISSN:2188-5079
DOI:10.34385/proc.47.B4L-E-2
PDF download (126.7KB)
Summary:
PSO network is the method of dividing population of PSO into multiple sub-swarm groups, and each sub-swarm group is connected based on network structure. In PSO network, the parameters which characterize network structure affect the search performances significantly. However, such an effect has not been investigated. In this paper, the deterministic PSO network with deterministic couplings is proposed. The proposed model does not have stochastic dynamics and has only deterministic dynamics. We investigate the characteristic of the D-PSON-D and perform the numerical experiments. We then clarify the suitable parameters for the network structure.